© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123704
    Prev
    Next
    INDEX
    Explanations

    so [feeling]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    赑
    -2.23
    b
    -2.16
     Their
    -2.13
     Schülerinnen
    -2.02
    에도
    -1.99
    欤
    -1.93
    >
    -1.92
    𞤢
    -1.92
    k
    -1.89
    m
    -1.87
    POSITIVE LOGITS
    
    1.84
     riuscito
    1.81
    weetened
    1.73
    💢
    1.71
    剜
    1.69
    📝
    1.68
    ⬇
    1.67
    ności
    1.67
    tolsó
    1.66
    kaç
    1.63
    Activations Density 0.009%

    No Known Activations